design-system-loading

design-system-loading is a cursor rule for Cursor from robertsfeir/atelier-pipeline. It costs 1,038 tokens per session, scanned A, original, Apache-2.0.

A shared rulebook for finding and applying a project's design system, including its colors, layout rules, and icons. It defines what to do when the system is configured, stored in a standard folder, or missing.

In plain words
What is it for?
Use it when agents create or change user interfaces and need to locate design rules and handle icons consistently.
Why use it?
It prevents different coding agents from making inconsistent interface decisions or loading unnecessary design files. It also gives projects a predictable fallback when no design system exists.

Cursor rule for Cursor

Written for Cursor: a Cursor plugin manifest. Also seen: mentions subagents.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/robertsfeir/atelier-pipeline/design-system-loading
Clone the repo
git clone --depth 1 https://github.com/robertsfeir/atelier-pipeline

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for design-system-loading

README.md
[![agentmods](https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/design-system-loading.svg)](https://agentmods.dev/rules/robertsfeir/atelier-pipeline/design-system-loading)
Your own site
<a href="https://agentmods.dev/rules/robertsfeir/atelier-pipeline/design-system-loading"><img src="https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/design-system-loading.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,038 This file is loaded in full into every session.
When invoked 1,038 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.01038 $0.01038
Opus 5 $0.00519 $0.00519
Sonnet 5 $0.00208 $0.00208
Haiku 4.5 $0.00104 $0.00104

Measured 6d ago against content hash f5423b457f64, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

design-system-loading scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor-plugin/rules/design-system-loading.mdc · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design System Loading Reference

This document is the single source of truth for design system detection, selective loading, cross-agent consistency, and icon handling. Agent personas reference this doc rather than duplicating the rules inline.

Detection Order

When an agent begins work that touches UI, it must resolve the design system path using this three-step detection order:

  1. Read design_system_path from pipeline-config.json. If the value is non-null and non-empty, use that path as the design system directory. Config overrides convention -- if both a configured path and a design-system/ directory at the project root exist, the configured path takes precedence.

  2. Otherwise, check if design-system/ exists at the project root. If it does, use that as the design system directory.

  3. If neither exists, proceed without a design system. No error, no warning beyond the agent-level annotation ("no design system found"). This is not a failure condition.

Missing key: If design_system_path is absent from pipeline-config.json (pre-existing installs that predate ADR-0040), treat the missing key as null and fall through to step 2. Agents must not crash on a missing key.

tokens.md required: Once a design system directory is resolved, check that tokens.md exists inside it. If tokens.md is missing, log "tokens.md not found at [path] -- proceeding without design system" and treat the result as no design system found (step 3 behavior). Do not load other design system files without tokens.md.

Selective Loading Rules

When a design system is detected and tokens.md is confirmed present, load tokens.md (always) plus one domain-specific file based on the work being done:

Building... Load
Any UI tokens.md (always)
Components, forms + components.md
Navigation + navigation.md
Dashboards, data display + data-viz.md
Marketing/web pages + layouts-web.md
App screens + layouts-app.md

Read the full file on GitHub · 114 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 114 lines · 1,038 tokens per session scan A f5423b457f64

Subscribe to this mod's changes

design-system-loading is a cursor rule published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,038 tokens to every session, about $0.0052 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.